@conference {Radev2020, title = {BayesFlow: Learning complex stochastic models with invertible neural networks}, year = {2020}, abstract = {Estimating the parameters of mathematical models is a common problem in almost all branches of science. However, this problem can prove notably difficult when processes and model descriptions become increasingly complex and an explicit likelihood function is not available. With this work, we propose a novel method for globally amortized Bayesian inference based on invertible neural networks which we call BayesFlow. The method uses simulation to learn a global estimator for the probabilistic mapping from observed data to underlying model parameters. A neural network pre-trained in this way can then, without additional training or optimization, infer full posteriors on arbitrary many real data sets involving the same model family. In addition, our method incorporates a summary network trained to embed the observed data into maximally informative summary statistics. Learning summary statistics from data makes the method applicable to modeling scenarios where standard inference techniques with hand-crafted summary statistics fail. We demonstrate the utility of BayesFlow on challenging intractable models from population dynamics, epidemiology, cognitive science and ecology. We argue that BayesFlow provides a general framework for building reusable Bayesian parameter estimation machines for any process model from which data can be simulated.}, url = {http://arxiv.org/abs/2003.06281}, author = {Radev, Stefan T. and Mertens, Ulf K. and Voss, Andreass and Lynton Ardizzone and K{\"o}the, Ullrich} } @conference {Sorrenson2020, title = {Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)}, booktitle = {Intl. Conf. Learning Representations (ICLR)}, year = {2020}, abstract = {A central question of representation learning asks under which conditions it is possible to reconstruct the true latent variables of an arbitrarily complex generative process. Recent breakthrough work by Khemakhem et al. (2019) on nonlinear ICA has answered this question for a broad class of conditional generative processes. We extend this important result in a direction relevant for application to real-world data. First, we generalize the theory to the case of unknown intrinsic problem dimension and prove that in some special (but not very restrictive) cases, informative latent variables will be automatically separated from noise by an estimating model. Furthermore, the recovered informative latent variables will be in one-to-one correspondence with the true latent variables of the generating process, up to a trivial component-wise transformation. Second, we introduce a modification of the RealNVP invertible neural network architecture (Dinh et al. (2016)) which is particularly suitable for this type of problem: the General Incompressible-flow Network (GIN). Experiments on artificial data and EMNIST demonstrate that theoretical predictions are indeed verified in practice. In particular, we provide a detailed set of exactly 22 informative latent variables extracted from EMNIST.}, url = {http://arxiv.org/abs/2001.04872}, author = {Sorrenson, Peter and Rother, Carsten and K{\"o}the, Ullrich} } @article {Wolf2020, title = {The Mutex Watershed and its Objective: Efficient, Parameter-Free Graph Partitioning}, journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, volume = {43}, year = {2020}, pages = {3724-3738}, abstract = {Image partitioning, or segmentation without semantics, is the task of decomposing an image into distinct segments, or equivalently to detect closed contours. Most prior work either requires seeds, one per segment; or a threshold; or formulates the task as multicut / correlation clustering, an NP-hard problem. Here, we propose a greedy algorithm for signed graph partitioning, the "Mutex Watershed". Unlike seeded watershed, the algorithm can accommodate not only attractive but also repulsive cues, allowing it to find a previously unspecified number of segments without the need for explicit seeds or a tunable threshold. We also prove that this simple algorithm solves to global optimality an objective function that is intimately related to the multicut / correlation clustering integer linear programming formulation. The algorithm is deterministic, very simple to implement, and has empirically linearithmic complexity. When presented with short-range attractive and long-range repulsive cues from a deep neural network, the Mutex Watershed gives the best results currently known for the competitive ISBI 2012 EM segmentation benchmark.}, doi = {10.1109/tpami.2020.2980827}, author = {Wolf, Steffen and Bailoni, Alberto and Pape, Constantin and Rahaman, Nasim and Kreshuk, Anna and K{\"o}the, Ullrich and Hamprecht, Fred A.} } @article {Kleesiek2019, title = {Can Virtual Contrast Enhancement in Brain MRI Replace Gadolinium?: A Feasibility Study}, journal = {Investigative Radiology}, volume = {54}, year = {2019}, pages = {653{\textendash}660}, abstract = {Objectives Gadolinium-based contrast agents (GBCAs) have become an integral part in daily clinical decision making in the last 3 decades. However, there is a broad consensus that GBCAs should be exclusively used if no contrast-free magnetic resonance imaging (MRI) technique is available to reduce the amount of applied GBCAs in patients. In the current study, we investigate the possibility of predicting contrast enhancement from noncontrast multiparametric brain MRI scans using a deep-learning (DL) architecture. Materials and Methods A Bayesian DL architecture for the prediction of virtual contrast enhancement was developed using 10-channel multiparametric MRI data acquired before GBCA application. The model was quantitatively and qualitatively evaluated on 116 data sets from glioma patients and healthy subjects by comparing the virtual contrast enhancement maps to the ground truth contrast-enhanced T1-weighted imaging. Subjects were split in 3 different groups: Enhancing tumors (n = 47), nonenhancing tumors (n = 39), and patients without pathologic changes (n = 30). The tumor regions were segmented for a detailed analysis of subregions. The influence of the different MRI sequences was determined. Results Quantitative results of the virtual contrast enhancement yielded a sensitivity of 91.8\% and a specificity of 91.2\%. T2-weighted imaging, followed by diffusion-weighted imaging, was the most influential sequence for the prediction of virtual contrast enhancement. Analysis of the whole brain showed a mean area under the curve of 0.969 {\textpm} 0.019, a peak signal-to-noise ratio of 22.967 {\textpm} 1.162 dB, and a structural similarity index of 0.872 {\textpm} 0.031. Enhancing and nonenhancing tumor subregions performed worse (except for the peak signal-to-noise ratio of the nonenhancing tumors). The qualitative evaluation by 2 raters using a 4-point Likert scale showed good to excellent (3-4) results for 91.5\% of the enhancing and 92.3\% of the nonenhancing gliomas. However, despite the good scores and ratings, there were visual deviations between the virtual contrast maps and the ground truth, including a more blurry, less nodular-like ring enhancement, few low-contrast false-positive enhancements of nonenhancing gliomas, and a tendency to omit smaller vessels. These "features" were also exploited by 2 trained radiologists when performing a Turing test, allowing them to discriminate between real and virtual contrast-enhanced images in 80\% and 90\% of the cases, respectively. Conclusions The introduced model for virtual gadolinium enhancement demonstrates a very good quantitative and qualitative performance. Future systematic studies in larger patient collectives with varying neurological disorders need to evaluate if the introduced virtual contrast enhancement might reduce GBCA exposure in clinical practice.}, keywords = {Bayesian uncertainty, deep learning, gadolinium-based contrast agents, glioma, multiparametric MRI}, issn = {15360210}, doi = {10.1097/RLI.0000000000000583}, author = {Kleesiek, Jens and Morshuis, Jan Nikolas and Isensee, Fabian and Deike-Hofmann, Katerina and Paech, Daniel and Kickingereder, Philipp and K{\"o}the, Ullrich and Rother, Carsten and Forsting, Michael and Wick, Wolfgang and Bendszus, Martin and Schlemmer, Heinz Peter and Radbruch, Alexander} } @conference {Kroeger-2014, title = {Asymmetric Cuts: Joint Image Labeling and Partitioning}, booktitle = {36th German Conference on Pattern Recognition}, year = {2014}, author = {Kr{\"o}ger, Thorben and Kappes, J{\"o}rg H. and Thorsten Beier and K{\"o}the, Ullrich and Fred A. Hamprecht} }